Filters








14,874 Hits in 8.0 sec

Automatic classification of hand drawn geometric shapes using constructional sequence analysis

R.M. Guest, S. Chindaro, M.C. Fairhurst, J.M. Potter
Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.  
A method for automatically assessing the constructional sequence from a neuropsychological drawing task using Hidden Markov Models is presented.  ...  We also present a method of extracting and identifying the position of individual pen strokes relating to individual sides of a shape within a drawing to form training and testing sequences.  ...  Acknowledgements The authors acknowledge the support of the UK Engineering and Physical Science Research Council. References  ... 
doi:10.1109/icdar.2003.1227808 dblp:conf/icdar/GuestCFP03 fatcat:aazzw3sxrfbvxnidr5vomsaany

Experimental evaluation of an on-line scribble recognizer

Manuel J. Fonseca, Joaquim A. Jorge
2001 Pattern Recognition Letters  
We present a fast, simple and compact approach to recognize Scribbles (multi-stroke geometric shapes) drawn with a stylus on a digitizing tablet.  ...  Our method is able to identify shapes of different sizes and rotated at arbitrary angles, drawn with dashed, continuous strokes or overlapping lines.  ...  With this editor users can create geometric shapes and invoke commands using hand drawn sketches. Shapes can be drawn, copied, moved and resized, using just the pen.  ... 
doi:10.1016/s0167-8655(01)00076-9 fatcat:4nptcskyfrbpxpscf3qxhvbuuy

An Efficient Approach for Video Action Classification Based on 3D Zernike Moments [chapter]

I. Lassoued, E. Zagrouba, Y. Chahir
2011 Communications in Computer and Information Science  
The originality of this approach consists to represent actions in video sequences by a three-dimension shape obtained from different silhouettes in the space-time volume.  ...  This paper proposes a new method for video action classification based on 3D Zernike moments. These last ones aim to capturing both structural and temporal information of a time varying sequence.  ...  So, video indexation and retrieval by automatic content analysis is now one of the major goals in information systems.  ... 
doi:10.1007/978-3-642-22309-9_24 fatcat:zmipkftmxray5aqsi427edc3si

Parsing Architecture within Plan Drawings with Application to Medieval Castles and Fortresses [article]

Andrew Willis, Yunfeng Sui, Katharina Galor
2009 VAST: International Symposium on Virtual Reality  
The estimated values are used to automatically generate a 3D structure using the estimated semantic labels of structural elements in the plan drawing.  ...  These drawings include important geometric information such as the location, shape, and size of architectural features, which, for decaying or collapsed structures, may be the only existing records of  ...  Much (almost all) of which is typically in analog, i.e., paper, form be it photographic, hand drawn, or the written word.  ... 
doi:10.2312/vast/vast09/017-024 fatcat:myzytfqo4bgonfu2kdlv43m34y

Page 1383 of Mathematical Reviews Vol. 56, Issue 4 [page]

1978 Mathematical Reviews  
of scenes consisting of planar geometrical shapes (pp. 838-843); E.  ...  Radhakrishnan, Recognition of hand-drawn flowcharts (pp. 424-428); Robert M. Haralick, The table look-up rule (pp. 447-454); Ashok V. Kulkarni and Laveen N.  ... 

Combining geometry and domain knowledge to interpret hand-drawn diagrams

Leslie Gennari, Levent Burak Kara, Thomas F. Stahovich, Kenji Shimada
2005 Computers & graphics  
One main challenge in building interpreters for hand-drawn sketches is the task of parsing a sketch to locate the individual symbols.  ...  An evaluation of our interface has indicated that, even for novice users, our system can successfully locate and identify most of the circuit components in hand-drawn circuit diagrams. r  ...  Our recognizer uses training examples to construct a probabilistic definition model of each symbol, based on geometric features of the segments.  ... 
doi:10.1016/j.cag.2005.05.007 fatcat:rgt2rqui2vgbdhhleqjz4gcjge

Analysis of Leonardo da Vinci's Architecture through Parametric Modeling: A Method for the Digital Reconstruction of the Centrally Planned Churches Depicted in Ms. B

Beatrice Vaienti, Fabrizio Ivan Apollonio, Marco Gaiani
2020 Heritage  
Then, the geometric process for the construction of the plan and its relationship with the elevation measures were studied for each church.  ...  To understand the reasons behind the use of this original technique, the edifices' shape and classify them, we decided to use 3D digital reconstruction techniques, for their ability to avoid misunderstandings  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/heritage3040063 fatcat:6iepgxdwqvhcbi3uekecnjpdnq

SUMLOW: early design‐stage sketching of UML diagrams on an E‐whiteboard

Qi Chen, John Grundy, John Hosking
2008 Software, Practice & Experience  
Most visual diagramming tools provide point-and-click construction of computer-drawn diagram elements using a conventional desktop computer and mouse.  ...  SUMLOW allows designers to sketch UML constructs, mixing different UML diagram elements, diagram annotations and hand-drawn text.  ...  It differs from other sketching-based UML design tools in its preservation of hand-drawn sketches and emphasis on gesturebased manipulation of these hand-drawn, whiteboard-like sketches.  ... 
doi:10.1002/spe.856 fatcat:onla3ilmavcrfbboohrnkgl2ra

Automatic Recognition of Colloquial Australian Sign Language

Eun-Jung Holden, Gareth Lee, Robyn Owens
2005 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1  
The features represent the relative geometrical positioning and shapes of the target objects, as well as their directions of motion.  ...  This paper presents an automatic Australian sign language (Auslan) recognition system, which tracks multiple target objects (the face and hands) throughout an image sequence and extracts features for the  ...  Using a clustering technique, they generate clusters of hand shapes on an eigenspace, which are then used for classification.  ... 
doi:10.1109/acvmot.2005.30 dblp:conf/wacv/HoldenLO05 fatcat:jkevoeqtrjcfdog37ev4ydyuam

Automated Feature Extraction from UML Images to Measure SOA Size

2020 International journal of recent technology and engineering  
Enormous development has been experiences in the field of text and image extraction and classification.  ...  This study propose an automatic tool based on existing deep learning algorithms including ResNet50 CNN to read UML interface and sequence diagrams images to detect UML arrows, EAST test detector to detect  ...  Problems of geometrical counter and area based detection can be solved by introducing machine learning techniques to take care of different types of shapes, shades, area and colors.  ... 
doi:10.35940/ijrte.b4131.079220 fatcat:f473c7m6tngwrfhzelnk3qceay

Recognition of Hand Printed Characters Based on Simple Geometric Features

Halawani
2010 Journal of Computer Science  
Most of these data are in hand printed form and very large; therefore the use of automatic recognition technique of hand printed character by machine is essential to achieve an efficient way of high speed  ...  Problem statement: The use of computers in information processing technology nowadays is one of the main trends of office automation.  ...  Fig. 1 : 1 Quadrants used in feature location Fig. 2 : 2 Sample Fig. 3 : 3 Samples of off-line hand printed charactersRecognition scheme: Recognition process occurs as in the following sequence:  ... 
doi:10.3844/jcssp.2010.1518.1523 fatcat:ahxg7nkykvh5fgxwbl366el3be

Recognition of Hand Printed Characters Based on Simple Geometric Features

Halawani
2010 Journal of Computer Science  
Most of these data are in hand printed form and very large; therefore the use of automatic recognition technique of hand printed character by machine is essential to achieve an efficient way of high speed  ...  Problem statement: The use of computers in information processing technology nowadays is one of the main trends of office automation.  ...  Fig. 1 : 1 Quadrants used in feature location Fig. 2 : 2 Sample Fig. 3 : 3 Samples of off-line hand printed charactersRecognition scheme: Recognition process occurs as in the following sequence:  ... 
doi:10.3844/jcssp.2010.1512.1517 fatcat:bmtfglsthbhlldu6n2322u7ou4

Protein Structure Classification [chapter]

Patrice Koehl
2006 Reviews in computational chemistry  
I review the properties of protein structures, with a special interest on their geometry. Computer methods for the automatic comparison and classification of these structures are then reviewed.  ...  Years of research in biology have established that all cellular functions are deeply connected to the shape of their molecular actors.  ...  Acknowledgments PK acknowledges support from the National Science Foundation (Grant CCR-00-86013) and from the National Institute of Health (GM 63817).  ... 
doi:10.1002/0471780367.ch1 fatcat:ykk7nbob4fbc5awgqlscved4ua

A region-based object tracking scheme using Adaboost-based feature selection

Fan-Tung Wei, Sheng-Ting Chou, Chia-Wen Lin
2008 2008 IEEE International Symposium on Circuits and Systems  
The proposed mechanism is composed of two trackers. The first tracker extract video objects by using Adaboost on pixel-based global seed features. it can provide more detailed segmentation of target.  ...  A confidence measure is proposed to minimize the effort of human interactions.  ...  Fig. 6 . 6 Object extraction result of right-hand-side person in the Hall sequence using the proposed method. Fig. 7 . 7 Accuracy ratio with the proposed method for the Hall sequence.  ... 
doi:10.1109/iscas.2008.4542027 dblp:conf/iscas/WeiCL08 fatcat:jeo5cbqzkjfc7fk4sompx3tyna

Mode detection in on-line pen drawing and handwriting recognition

D. Willems, S. Rossignol, L. Vuurpijl
2005 Eighth International Conference on Document Analysis and Recognition (ICDAR'05)  
The system consists of three kNN classifiers which use global and structural features of the pen trajectory and a fitting algorithm for verifying the different geometrical objects.  ...  Results are presented on a significant amount of data, acquired in different contexts like scribble matching and design applications.  ...  We would also like to thank Manuel Fonseca for making his data available to us.  ... 
doi:10.1109/icdar.2005.160 dblp:conf/icdar/WillemsRV05 fatcat:yglr54m6kveixgnnd3trlftfuq
« Previous Showing results 1 — 15 out of 14,874 results